|
|
Hardware Acceleration Using Functional Languages
Hodaňová, Andrea ; Kadlček, Filip (referee) ; Fučík, Otto (advisor)
The aim of this thesis is to research how the functional paradigm can be used for hardware acceleration with an emphasis on data-parallel tasks. The level of abstraction of the traditional hardware description languages, such as VHDL or Verilog, is becoming to low. High-level languages from the domains of software development and modeling, such as C/C++, SystemC or MATLAB, are experiencing a boom for hardware description on the algorithmic or behavioral level. Functional Languages are not so commonly used, but they outperform imperative languages in verification, the ability to capture inherent paralellism and the compactness of code. Data-parallel task are often accelerated on FPGAs, GPUs and multicore processors. In this thesis, we use a library for general-purpose GPU programs called Accelerate and extend it to produce VHDL. Accelerate is a domain-specific language embedded into Haskell with a backend for the NVIDIA CUDA platform. We use the language and its frontend, and create a new backend for high-level synthesis of circuits in VHDL.
|
|
|
General-Purpose Computation Using Graphics Card
Boček, Michal ; Pospíchal, Petr (referee) ; Jaroš, Jiří (advisor)
This thesis describes the programming models OpenCL and CUDA for Parallel Programming adapters and in case of OpenCL even for other computing platforms. There was implemented the application which calculates the electric potential in the crystalline lattice. The algorithm was programmed using two technologies for the GPU - OpenCL and CUDA. Their computational time were compared together with computational time of the CPU.
|
|
|
GPU-Accelerated Synthesis of Probabilistic Programs
Marcin, Vladimír ; Matyáš, Jiří (referee) ; Češka, Milan (advisor)
V tejto práci sa zoberáme problémom automatizovanej syntézy pravdepodobnostných programov: majme konečnú rodinu kandidátnych programov, v ktorej chceme efektívne identifikovať program spĺňajúci danú špecifikáciu. Aj riešenie tých najjednoduchších syntéznych problémov v praxi predstavuje NP-ťažký problém. Pokrok v tejto oblasti prináša nástroj Paynt, ktorý na riešenie tohto problému používa novú integrovanú metódu syntézy pravdepodobnostných programov. Aj keď sa tento prístup dokáže efektívne vysporiadať s exponenciálnym rastom rodín kandidátnych riešení, stále tu existuje problém spôsobený exponenciálnym rastom jednotlivých členov týchto rodín. S cieľom vysporiadať sa aj s týmto problémom, sme implementovali GPU orientované algoritmy slúžiace na overovanie kandidátnych programov (modelov), ktoré danú úlohu paralelizujú na stavovej úrovni pravdepodobnostých modelov. Celkové zrýchlenie doshiahnuté týmto prístupom za určitých podmienok potom prinieslo takmer teoretický limit možného zrýchlenia syntézneho procesu.
|
|
| |
|
|
Parallel Training of Neural Networks for Speech Recognition
Veselý, Karel ; Fousek, Petr (referee) ; Burget, Lukáš (advisor)
This thesis deals with different parallelizations of training procedure for artificial neural networks. The networks are trained as phoneme-state acoustic descriptors for speech recognition. Two effective parallelization strategies were implemented and compared. The first strategy is data parallelization, where the training is split into several POSIX threads. The second strategy is node parallelization, which uses CUDA framework for general purpose computing on modern graphic cards. The first strategy showed a 4x speed-up, while using the second strategy we observed nearly 10x speed-up. The Stochastic Gradient Descent algorithm with error backpropagation was used for the training. After a short introduction, the second chapter of this thesis shows the motivation and introduces the neural networks into the context of speech recognition. The third chapter is theoretical, the anatomy of a neural network and the used training method are discussed. The following chapters are focused on the design and implementation of the project, while the phases of the iterative development are described. The last extensive chapter describes the setup of the testing system and reports the experimental results. Finally, the obtained results are concluded and the possible extensions of the project are proposed.
|
|
|
Simulation of Heat Diffusion in the Brain Using High-Level GPGPU Techniques
Krbila, Martin ; Kadlubiak, Kristián (referee) ; Jaroš, Jiří (advisor)
This master's thesis deals with acceleration of heat diffusion simulation using graphics cards. It describes an approach to acceleration of an existing implementation in Matlab, which is a part of k-Wave package. Various high-level as well as low-level libraries for GPU programming are introduced here and their strengths and weaknesses compared. A complete implementation of the simulation on GPU was created as a part of this work. This implementation achieves around hundredfold speedup over the existing CPU solution in Matlab. A module for computation of discrete trigonometric transformations on graphics card was created to accelerate simulation with various boundary conditions. This module achieves around ten times speedup over the best CPU implementation. Another output of this thesis is a performance comparison of several implementations of basic diffusion simulation each using a different GPGPU technique.
|
|
|
Parallelisation of Ultrasound Simulations on Multi-GPU Clusters
Dujíček, Aleš ; Kula, Michal (referee) ; Jaroš, Jiří (advisor)
This work is part of the k-Wave project, which is a toolbox designed for time ultrasound simulations in complex and heterogeneous media. The simulation functions are based on the k-space pseudospectral method. The goal of this work is to compute these simulations on graphics cards using local domain decompostion. Thanks to decomposition we could compute these simulations faster, and on larger data grids. The main goal of this work is to achieve efficiency and scalability.
|
|
|
Image classification using artificial intelligence
Labuda, Adam ; Přinosil, Jiří (referee) ; Burget, Radim (advisor)
This bachelor's thesis address the issue of classification and feature extraction of imagesfrom image. In JAVA platform will create an example that loads a set of images, extracted from symptoms with the help of artificial intelligence provided by the thesis supervisor. Artificial intellihence assumed kind of image. Finally the results are compared. }
|
|
|
Exploitation of GPU in graphics and image processing algorithms
Jošth, Radovan ; Svoboda, David (referee) ; Trajtel,, Ľudovít (referee) ; Herout, Adam (advisor)
Táto práca popisuje niekoľko vybraných algoritmov, ktoré boli primárne vyvinuté pre CPU procesory, avšak vzhľadom k vysokému dopytu po ich vylepšeniach sme sa rozhodli ich využiť v prospech GPGPU (procesorov grafického adaptéra). Modifikácia týchto algoritmov bola zároveň cieľom nášho výskumu, ktorý bol prevedený pomocou CUDA rozhrania. Práca je členená podľa troch skupín algoritmov, ktorým sme sa venovali: detekcia objektov v reálnom čase, spektrálna analýza obrazu a detekcia čiar v reálnom čase. Pre výskum detekcie objektov v reálnom čase sme zvolili použitie LRD a LRP funkcií. Výskum spektrálnej analýzy obrazu bol prevedný pomocou PCA a NTF algoritmov. Pre potreby skúmania detekcie čiar v reálnom čase sme používali dva rôzne spôsoby modifikovanej akumulačnej schémy Houghovej transformácie. Pred samotnou časťou práce venujúcej sa konkrétnym algoritmom a predmetu skúmania, je v úvodných kapitolách, hneď po kapitole ozrejmujúcej dôvody skúmania vybranej problematiky, stručný prehľad architektúry GPU a GPGPU. Záverečné kapitoly sú zamerané na konkretizovanie vlastného prínosu autora, jeho zameranie, dosiahnuté výsledky a zvolený prístup k ich dosiahnutiu. Súčasťou výsledkov je niekoľko vyvinutých produktov.
|
|
|
Fast Tissue Image Reconstruction Using a Graphics Card
Kadlubiak, Kristián ; Kula, Michal (referee) ; Jaroš, Jiří (advisor)
The photoacoustic spectroscopy is a recently developed imaging method that finds applications in many scientific fields such as medicine, biochemistry, materials engineering and many others. The photoacoustic spectroscopy finds particularly nice applications in medicine due to its properties such as non-invasiveness, non-aggressiveness and great accuracy. The source of this accuracy lies in advanced time-consuming calculations including operations like FFT and trilinear interpolation. This thesis is dedicated to the acceleration of this technique on a graphics card. In our implementation, we have taken a full advantage of various features provided in modern GPUs such as shared memory and texture hardware. Our implementation has been tested on one of the most powerful GPU designed for high performance computing, namely NVIDIA K20m. In this environment, our application speeds up certain parts of reconstruction by a factor above 400. In a single run mode, the whole reconstruction runs a bit longer than the pure MATLAB version due to the necessity of transferring data between MATLAB and the CUDA code, although the developed approach reduced the data transfers between MATLAB and GPU by 37%. The real potential of the implementation reveals while processing large batches of photoacoustic images.
|
guest ::
